Implementing quality-by-design latent-variable model predictive control (QbD-LV-MPC) for batch processes: An updating policy for batch profiles

The present work addresses the problem of loss of model validity in batch process control via online monitoring and adaptation based model predictive control. To this end, a state space subspace-based model identification method suitable for batch processes is utilized and then a model predictive controller is designed. To monitor model performance, a model validity index is developed for batch processes. In the event of poor prediction (observed via breaching of a threshold by the model validity index), reidentification is triggered to identify a new model and thus adapt the controller. In order to capture the most recent process dynamics, the identification is appropriately designed to emphasize more the recent process data. The efficacy of the proposed method is demonstrated using an electric arc furnace as a simulation test bed.

Batch process is widely applied in pharmaceutical, paint, food and beverage industries etc. In Batch process specific amount of input feed is passing through desired set of equipment for a specified amount of time to get a definite amount of valuable output product. In batch process, temperature of batch reactor is very important parameter. This temperature loop is mostly controlled through PID controller, but for precise control and plant optimization of batch process are performed by some advanced control strategies like fuzzy, MPC (Model Predictive Control), neural etc. In industries these advanced control schemes implemented through DCS (Distributed Control System), PLCs (Programmable Logic Controller). For communication with dif- ferent make controllers user can use various communication protocol such as Modbus TCP, Modbus RTU, Ethernet, Profibus, Profinet etc. In this experiment Modbus RTU, Modbus TCP communication protocol are used for communication and control of batch process from remote controllers.

Model-based solutions for monitoring and control of chemical batch processes have been of interest in research for many decades. However, unlike in continuous processes, in which model-based tools such as Model Predictive Control (MPC) have become a standard in the industry, the reported use of models for batch processes, either for monitoring or control, is rather scarce. This limited use is attributed partly to the inherent complexity of the batch processes (e. g., dynamic, nonlinear, multipurpose) and partly to the lack of appropriate commercial tools in the past. In recent years, algorithms and commercial tools for model-based monitoring and control of batch processes have become more mature and in the era of Industry 4.0 and digitalization they are slowly but steadily gaining more interest in real-word batch applications. This contribution provides a practical example in this application field. Specifically, the use of a grey-box modeling approach, in which a multiway Projection to Latent Structure (PLS) model is combined with a first-principles model, to monitor the evolution of a batch polymerization process and predict in real-time the final batch quality is reported. The modeling approach is described, and the experimental results obtained from an industrial batch laboratory reactor are presented.

This paper summarizes recent progress in the area of estimation and control of batch processes. The task of designing effective strategies for the estimation of unmeasured variables and for the control of the important outputs of the process is linked to our need to optimize the process and its success is depended upon the availability of a process model. For this reason we will provide a substantial focus on the modeling issues that relate to batch processes. In particular we will focus attention on the approach developed in our group and referred to as “tendency modeling” that can be used for the estimation, optimization and control of batch processes. Several batch reactor example processes will be detailed to illustrate the applicability of the general approach. These relate to organic synthesis reactors and bioreactors. The point that distinguishes tendency modeling from other modeling approaches is that the developed Tendency Models are multivariable, nonlinear, and aim to incorporate all the available fundamental information about the process through the use of material and energy balances. These models are not frozen in time as they are allowed to evolve. Because they are not perfectly accurate they are used in the optimization, estimation and control of the process on a tentative basis as they are updated either between batches or more frequently. This iterative or adaptive modeling strategy also influences the controller design. The controller performance requirements and thus the need of a more accurate model increase as successive optimization steps guide the process operation near its constraints.

The prevalence of batch and batch-like operations, in conjunction with the continued resurgence of artificial intelligence techniques for clustering and classification applications, has increasingly motivated the exploration of the applicability of deep learning for modeling and feedback control of batch and batch-like processes. To this end, the present study seeks to evaluate the viability of artificial intelligence in general, and neural networks in particular, toward process modeling and control via a case study. Nonlinear autoregressive with exogeneous input (NARX) networks are evaluated in comparison with subspace models within the framework of model-based control. A batch polymethyl methacrylate (PMMA) polymerization process is chosen as a simulation test-bed. Subspace-based state-space models and NARX networks identified for the process are first compared for their predictive power. The identified models are then implemented in model predictive control (MPC) to compare the control performance for both modeling approaches. The comparative analysis reveals that the state-space models performed better than NARX networks in predictive power and control performance. Moreover, the NARX networks were found to be less versatile than state-space models in adapting to new process operation. The results of the study indicate that further research is needed before neural networks may become readily applicable for the feedback control of batch processes.

A barely approached of the topics in the area of Batch Process (BP) Control is controllability and stability analysis. This is because the dynamic characteristic of BPs makes the traditional analysis of these properties harder. Characteristics like the transitory dynamics of the states and the irreversibility of the states (from the dynamic systems point of view) are serious obstacles for the use of classic tools to make an analysis of stability and controllability in BP, therefore, other tools should be used in order to come closer to a theoretical analysis on BP control. One approach is the use of some set theory's definitions. This paper uses the Controllable Trajectories Sets (CTS) to carry out a theoretical analysis on BP control.

Robust identification and control of batch processes

Cyber physical systems (CPS), which realize the real-time perception, dynamic control and information services of large-scale engineering systems through the organic integration and deep collaboration of 3C (Computer, Communication, Control) technologies, are a highly anticipated technology to solve the issues of modern plants innovatively. The significance of CPS is to connect the physical device to the internet, allowing the physical device to have five functions of computing, communication, precise control, remote coordination and autonomy. Among these CPS technologies used in industrial processes, economic model predictive control (MPC), which is a control scheme for industrial process with optimization economic as an indicator, is considered a forerunner approach towards plant process automation. However, most published papers on economic MPC applications have focused on continuous processes and only a few researchers have turned their attention to batch processes. This research studies economic MPC strategies for batch processes to evaluate its applicability. Most batch processes exhibit highly nonlinear and time-varying behavior, which makes it difficult to control them. We applied economic MPC and PID control scheme to a batch process, observing that economic MPC scheme showed better control performance in speed, disturbance suppression and efficiency. Moreover, from a simulation result of max production rate control with economic MPC, it was revealed that process constraints affect production rate considerably, which indicates that economic MPC can be used not only for process control but also for process design. Off-line study with economic MPC can assess the effect of plant specification on plant efficiency quantitively. This paper revealed that economic MPC can improve both design and control of batch processes.

From an engineering perspective, the term process refers to a conversion of raw materials into intermediate or final products using chemical, physical, or biological operations. Industrial processes can be performed either in continuous or in batch mode. There exist for instance continuous and batch units for reaction, distillation, and crystallization. In batch mode, the raw materials are loaded in the unit only at the beginning of the process. Subsequently, the desired transformation takes place inside the unit, and the products are eventually removed altogether after the processing time. In order to obtain the desired production volume, several batches are repeated. In an industrial process, several variables such as temperatures, pressures, and concentrations have to be regulated in order to ensure safety, maintain the product quality, and optimize economic criteria. In principle, model-based control techniques available in the literature could be systematically utilized in order to achieve these goals. However, a limitation to the applicability of model-based techniques for batch process control is that the available models of batch processes often suffer from severe uncertainties. In this thesis, we have investigated the use of measured data in order to improve the performance of model-based control of batch processes. Our approach consists in using the measured data in order to refine from batch to batch the model that is used to design the controller. By doing so, the performance delivered by the model-based controller is expected to improve. We have developed the parametric model update technique Iterative Identification Control (IIC) and non-parametric model update technique Iterative Learning Control (ILC). While in IIC the measured batch data are used to update from batch to batch parameter estimates for the uncertain physical coefficients, in ILC the data are used to compute a non-parametric, additive correction term for a nominal process model. We have tested the ILC and IIC algorithms for the batch cooling crystallization process both in a simulation environment and on a real pilot-scale crystallization setup. We have shown that the two approaches have complementary advantages. On the one hand, the parametric approach allows for a faster learning since it produces a parsimonious representation of the process. On the other hand, the nonparametric approach can cope effectively with the serious issue of structural mismatches owing to the use of a more flexible representation. Furthermore, we have investigated the use of excitation signals to enhance the performance of parametric model update techniques in an iterative identification/controller design scheme similar to IIC. The excitation signals have a dual effect on the overall control performance. On the one hand, the application of an excitation signal superposed to the normal control input leads after identification to an increased model accuracy, and thus a better control performance. On the other hand, the excitation signal also causes a temporary performance degradation, since it acts as a disturbance while it is applied to control system. For linear dynamical systems, we have shown that the problem of designing the excitation signals aiming to maximize the overall control performance can be approximated as a convex optimization problem. The lack of generally applicable and computationally efficient experiment design tools for nonlinear systems is the main bottleneck for the optimal design of the excitation signals in the case of batch processes. In this thesis, we have developed a novel experiment design method applicable to the class of fading memory nonlinear system. Limiting the excitation signals to a finite number of levels, the information matrix can be expressed as a linear function of the frequency of occurrence of each possible pattern having duration equal to the memory of the system. Exploiting the linear relation between the frequencies and the information matrix, several experiment design problems can be formulated as convex optimization problems.

Just-in-time learning based integrated MPC-ILC control for batch processes

Near-optimal control of batch processes can often be obtained using simple feedback structures. The maximum gain rule for selection of good outputs for feedback control is extended to nonlinear tracking problems, such as found in control of batch processes.

Reinforcement learning for batch process control: Review and perspectives

This manuscript addresses the problem of leveraging thermal images for modeling and feedback control, specifically tailored for terminal quality control of batch processes. The primary objective, common in many batch processes, is to produce products with quality variables aligning with user specifications, available for measurement only at batch termination, precluding the direct use of classical control strategies. Furthermore, in many instances, traditional online sensors such as thermocouples may not be available, but instead spectral inputs like thermal images or acoustic data may be more readily available for feedback control. The challenge is to not only use the non-traditional sensor data for building a dynamic model but also to use that model for terminal quality control. The proposed approach involves a multi-layered modeling strategy. Initially, a dimensionality reduction technique is employed to condense the high-dimensional image into a set of representative outputs. Subsequently, subspace identification (SSID) is applied to develop a Linear Time-Invariant (LTI) State Space (SS) model between the inputs and the reduced outputs. Finally, a Partial Least Squares (PLS) model is constructed linking the terminal states of a batch (identified using SSID) with the product qualities obtained for that specific batch. This model is then incorporated into a Model Predictive Control (MPC) formulation. The effectiveness of the MPC is illustrated by showcasing its capability to generate products of high quality by deploying the MPC on a bi-axial lab-scale rotational molding setup.

Optimal control and operation of drum granulation processes

Integration of scheduling and control results in Mixed Integer Nonlinear Programming (MINLP) which is computationally expensive. The online implementation of integrated scheduling and control requires repetitively solving the resulting MINLP at each time interval. (Zhuge and Ierapetritou, Ind Eng Chem Res. 2012;51:8550–8565) To address the online computation burden, we incorporare multi‐parametric Model Predictive Control (mp‐MPC) in the integration of scheduling and control. The proposed methodology involves the development of an integrated model using continuous‐time event‐point formulation for the scheduling level and the derived constraints from explicit MPC for the control level. Results of case studies of batch processes prove that the proposed approach guarantees efficient computation and thus facilitates the online implementation. © 2014 American Institute of Chemical Engineers AIChE J, 60: 3169–3183, 2014